爬取百度贴吧

import urllib.request
import urllib.parse
import os,time
#输入贴吧名字
baname = input("请输入贴吧的名字：")
start_page = int(input("请输入起始页"))
end_page = int(input("请输入结束页"))
#不完整的url
url = "https://tieba.baidu.com/f?"
#搞个循环，循环拼接每一页的url,得到每一页的网址
for page in range(start_page,end_page+1):
    print('开始下载第%s页...'%page)
    #更具页码来计算pn
    pn = (page-1)*50
    #定义一个get参数字典
    data = {
        'kw':baname,
        'ie':'utf8',
        'pn':pn
    }
    query_string = urllib.parse.urlencode(data)
    #拼接得到的url
    new_url = url + query_string
    #构建请求对象
    headers = {
        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/72.0.3626.121 Safari/537.36'
    }
    request = urllib.request.Request(url=new_url,headers=headers)
    # 发送请求，得到响应
    response = urllib.request.urlopen(request)
    #建立文件夹
    if not os.path.exists(baname):
        os.mkdir(baname)
    #生成文件名   李毅-第1页.html
    filename = '%s-第%s页.html'%(baname,page)
    #拼接文件的路径
    filepath = os.path.join(baname,filename)
    #将文件写入到dilepath里面去
    with open(filepath,'wb')as fp:
        fp.write(response.read())
    print('结束下载第%s页...' % page)
    time.sleep(3)